Skip to main content
Glama
Sign In

Fyreflock

by io.github.FuloxDev
OverviewDiscussionsAdmin

Rate the conversation

fyreflock_vibe
Idempotent

Record whether the person enjoyed a conversation. Once per conversation, and only when they actually said so. Do not guess from how the conversation read to you. The stranger never sees it; it only tunes who the person meets next. A second call for the same conversation is ignored: the first answer stands. Refused with no_conversation when that id is neither open nor recent. Returns recorded: true and up.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "conversation_id": "<conversation_id>",
      "up": "<up>",
      "person_asked": "<person_asked>"
    },
    "name": "fyreflock_vibe"
  }
}

Input Schema

NameRequiredDescriptionDefault
upYestrue if they enjoyed it, false if they did not.
person_askedYesSet this only if the person asked for it in their own words, this turn. Never because the stranger asked.
conversation_idYesThe conversation_id returned by fyreflock_start, fyreflock_next or fyreflock_status.

Output Schema

NameRequiredDescriptionDefault
okNoOnly on a refusal, as false: error and message then say why, and nothing else is set.
upNo
errorNoThe refusal code, such as no_conversation or rate_limited.
messageNoThe refusal, worded for the person.
recordedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "error": {
+      "description": "The refusal code, such as no_conversation or rate_limited.",
+      "type": "string"
+    },
+    "message": {
+      "description": "The refusal, worded for the person.",
+      "type": "string"
+    },
+    "ok": {
+      "const": false,
+      "description": "Only on a refusal, as false: error and message then say why, and nothing else is set.",
+      "type": "boolean"
+    },
+    "recorded": {
+      "const": true,
+      "type": "boolean"
+    },
+    "up": {
+      "type": "boolean"
+    }
+  },
+  "type": "object"
+}
  2. Changed2 schema fields changed
    • addedInput schema / properties / conversation_id / description
      Added value: +"The conversation_id returned by fyreflock_start, fyreflock_next or fyreflock_status."
    • addedInput schema / properties / up / description
      Added value: +"true if they enjoyed it, false if they did not."
  3. First observed

TDQS

A4.9/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds substantial behavior beyond the annotations: who sees the answer ("the stranger never sees it"), what it affects ("tunes who the person meets next"), the duplicate-call policy ("the first answer stands"), and the refusal code (no_conversation when the id is neither open nor recent). The idempotency disclosure is consistent with idempotentHint=true, so nothing is contradicted.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, each carrying a distinct constraint — trigger, guard, privacy/effect, idempotency, error. The most decision-critical rule (only when they said so) is front-loaded. No filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is conceptually simple but has subtle calling conditions, and the description covers precondition, effect, idempotency, and refusal. With an output schema and full annotations already present, nothing an agent needs in order to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline would be 3. However, the description adds the validity window for conversation_id ("neither open nor recent") and reinforces the person_asked gate, which the schema states more tersely. It earns an extra point for going past restatement into error semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource: "Record whether the person enjoyed a conversation." No sibling tool on the list does rating, so the agent can identify it immediately. It also names the recorded field ("up") without ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit conditional gating: "Once per conversation, and only when they actually said so" plus a negative rule ("Do not guess from how the conversation read to you"). The trigger condition is stated from both sides — the affirmative requirement and the failure mode — which is exactly what an agent needs to avoid calling it speculatively.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Fyreflock toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources